🔌 Model Context Protocol

MCP Connectors: Claude connected to everything

The Model Context Protocol is the "USB-C of AI": an open standard connecting Claude to your apps, data and tools. Here's how it works and the must-have connectors.

What is MCP?

The Model Context Protocol (MCP) is an open protocol created by Anthropic in late 2024 and adopted today across the industry — including OpenAI and Google. It defines a standard way for an AI model to discover and use external tools: reading email, querying databases, creating tasks, posting to Slack…

Before MCP, every integration was a custom build. Now, any service can publish an MCP server and any compatible AI can use it instantly. There are over a thousand servers available, and the number grows every week.

📧

Gmail

Search threads, read emails, create drafts and organize with labels from Claude.

Official
📁

Google Drive

Search and read documents, sheets and slides from your Drive without leaving the chat.

Official
📅

Google Calendar

Check your agenda, create events and find open slots using natural language.

Official
💬

Slack

Read channels, summarize conversations and send messages to your team.

Popular
🐙

GitHub

Issues, pull requests, code review and full repository management.

Popular
📝

Notion

Create and edit pages, databases and wikis in your workspace.

Popular
🛒

Shopify

Manage products, orders, customers and analytics for your online store.

E-commerce
🗄️

PostgreSQL

Query your databases in natural language with generated, safe SQL.

Data

How to add a connector

In the Claude app, go to Settings → Connectors and pick from the directory. In Claude Code, one command is enough:

terminal# Add the GitHub MCP server claude mcp add github -- npx -y @modelcontextprotocol/server-github # Add a remote server by URL claude mcp add --transport http notion https://mcp.notion.com/mcp # List active connectors claude mcp list

The architecture in 20 seconds

An MCP server exposes three things: tools (actions the AI can execute), resources (data it can read) and prompts (reusable templates). The client — Claude, your IDE, or any compatible app — connects via stdio or HTTP and negotiates the available capabilities. Everything with explicit permissions: you decide what the AI can touch.

Security tips

  • Only install connectors from trusted sources (official directory, verified repositories).
  • Review permissions: a read-only connector can't modify anything.
  • For sensitive data, prefer local MCP servers over remote ones.
  • In teams, admins can control which connectors are allowed.

Combine them with skills and multiply

Connector = access. Skill = mastery. Together, Claude truly works for you.

⚡ Explore skills See prompts